NVIDIA is using AI to design its future PC chips

The so-called artificial intelligence is one of the buzzwords, the reason is that it allows you to automate and do things that were not possible before and it has all been thanks to the development in recent years in this field. That is why it is not surprising that NVIDIA uses AI to design chips. Which will include not only your future PC graphics cards, but the rest of your processors and solutions.

It is not the first time that we have talked about the use of artificial intelligence for the design of new chips, since a few months ago we already told you about the same news regarding Google. Moreover, with the strong commitment of Jen Hsun Huang’s company to artificial intelligence in the last five years, it should not surprise us that they have also automated the creation of new chips in this way.

NVIDIA is using AI to design its future PC chips

The design of a new chip is something very complex today. It can be compared on an architectural level to designing an entire city at once with several interconnected components. Which does not mean that future processors on the market will be designed by computers, but it does mean that they will be used for a better design. In particular, with regard to the distribution of components, for greater efficiency and performance, as well as to accelerate the time of deployment and, therefore, of launching in the market.

How does NVIDIA use AI to design chips?

Through one of the conferences that took place during the GTC, Bill Dally, chief scientist of NVIDIA and renowned professor, described the use of artificial intelligence to assist in the design of new chips. What will accelerate the deployment of these in the market. It must be taken into account that one of the most important parts in the design is the so-called Floorplan, which is the distribution of the different components inside the chip, including the internal wiring responsible for distributing the energy inside the chip, including the uploads and voltage drops within it.

Nowadays, and regardless of the company we are talking about, the fact of creating a chip is a titanic task and the thing is not only reduced to taking the different blocks and ordering them efficiently. Also within the same block, the use of AI to design chips at NVIDIA can give them a design with the same functionality, but much more efficient. What if we talk about lower latencies in caches or an RT Core for improved Ray Tracing?

In a clear and simple way, we are talking about the use of a technology that allows possible solutions to be obtained that, if developed by a human team, would take months of work to obtain a simple solution. After all, and seen from a certain point of view, a chip is nothing more than a logic puzzle with its different logic gates interconnected with each other in a specific way. And this is something we can teach an artificial intelligence.